Skip to main content
SpringerLink
Log in

Unexploded ordnance discrimination using time-domain electromagnetic induction and self-organizing maps

  • Original Paper
  • Published:
Stochastic Environmental Research and Risk Assessment Aims and scope Submit manuscript

Abstract

Self-organizing maps (SOM) are implemented for discrimination of geologic noise, buried metal objects and unexploded ordnance using the geophysical method of time-domain electromagnetic induction. The learning and misfit measures are based on a Euclidean metric. The U*-matrix method is shown to be a reliable tool for determining data clusters and cluster boundaries. The performance of SOM for data-type discrimination was tested using three synthetic, idealized geophysical datasets consisting of exponential, multi-exponential and stretched-exponential decaying transients. In addition, experimental data were acquired using a modified Geonics EM63 instrument. Results from the synthetic examples show that SOM clusters the data based on their functional origin, when represented using U*-matrices. The percentage of correct classification is 100%. Unsupervised learning using the field dataset obtained with the Geonics EM63 succeeded in producing a multi-clustered map in which the background transients cluster themselves and are separated from clusters associated with metal clutter objects and UXO. Even though in some cases the SOM did not produce a single cluster for each type of causative body, it was able to separate clutter data from target data by producing several small clusters. The results are encouraging in view of the heterogeneity and sparsity of the training dataset.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  • Baçaõ F, Loboa V, Painho M (2005) The self-organizing map, the Geo-SOM, and relevant variants for geosciences. Comput Geosci 31(2):155–163

    Article  Google Scholar 

  • Benavides A, Everett ME (2007) Non-linear inversion of controlled source multi-receiver electromagnetic induction data for unexploded ordnance using a continuation method. J Appl Geophys 61:243–253

    Article  Google Scholar 

  • Beran, LS (2004) Classification algorithms for discrimination of unexploded ordnance, Dissertation, University of British Columbia, BC, Canada

  • Billings SD (2004) Discrimination and classification of buried unexploded ordnance using magnetometry. IEEE Trans Geosci Remote Sens 42(6):1241–1251

    Article  Google Scholar 

  • Butler DK (2004) Report on a workshop on electromagnetic induction methods for UXO detection and discrimination. Lead Edge 23:766–770

    Article  Google Scholar 

  • Castro de Matos M, Manassi Osorio PL, Schroeder Johann PR (2007) Unsupervised seismic facies analysis using wavelet transform and self-organizing maps. Geophysics 72(1):19–21

    Google Scholar 

  • Christodoulou C, Georgiopoulos M (2001) Applications of neural networks in electromagnetics. Artech House, Boston

    Google Scholar 

  • Collins L, Zhang Y, Li J, Wang H, Carin L, Hart S, Rose-Pehrsson S, Nelson H, McDonald J (2001) A comparison of the performance of statistical and fuzzy algorithms for unexploded ordnance detection. IEEE Trans Fuzzy Syst 9(1):17–30

    Article  Google Scholar 

  • Commer M, Newman G (2004) A parallel finite-difference approach for 3D transient electromagnetic modeling with galvanic sources. Geophysics 69(5):1192–1202. doi:10.1190/1.1801936

    Article  Google Scholar 

  • Das Y, McFee JE, Toews J, Stuart GC (1990) Analysis of an electromagnetic induction detector for real-time location of buried objects. IEEE Trans Geosci Remote Sens 28(3):278–287

    Article  Google Scholar 

  • Erwin E, Obermeyer K, Schulten K (1992) Self-organizing maps: ordering, convergence properties and energy functions. Biol cybern 67:47–55

    Article  CAS  Google Scholar 

  • Essenreiter R, Karrenbach M, Treitel S (2001) Identification and classification of multiple reflections with self-organizing maps. Geophys Prospect 49(3):341–352

    Article  Google Scholar 

  • Everett ME, Benavides A, Pierce Jr. C (2005) An experimental study of the time-domain electromagnetic response of a buried conductive plate. Geophysics 70(1):G1–G7

    Article  Google Scholar 

  • Everitt B (1980) Cluster analysis, 2nd edn. Heinemann Ed. Books, New York

    Google Scholar 

  • Geonics Ltd. (2001) EM61 and EM63 metal detectors for unexploded ordnance (UXO) detection and characterization. Technical note. Geonics, Ltd, Mississauga, Ca

    Google Scholar 

  • Geonics Ltd. (2002) EM63 full time domain electromagnetic UXO detector. Operating instructions. Geonics, Ltd, Mississauga, Ca

    Google Scholar 

  • Haykin S (1994) Neural networks. Macmillan, New york

    Google Scholar 

  • Hsien-Cheng C, Kopaska-Merkelb DC, Hui-Chuan C (2002) Identification of lithofacies using Kohonen self-organizing maps. Comput Geosci 28:223–229

    Article  Google Scholar 

  • Kandel ER, Schwartz H (1981) Principles of neural science. North-Holland, Amsterdam

    Google Scholar 

  • Klose CD (2006) Self-organizing maps for geoscientific data analysis: geological interpretation of multidimensional geophysical data. Comput Geosci 10:265–277

    Article  Google Scholar 

  • Kohonen T (1984) Self-organization and associative memory. Springer, Heidelberg

    Google Scholar 

  • Kohonen T (2000) Self-organizing maps, 3rd edn. Springer, Berlin

    Google Scholar 

  • Lin Z, Fortier A, Bartel DC (2002) Classification of salt-contaminated velocities with self-organizing map neural network. Lead Edge 21:1193–1196

    Article  Google Scholar 

  • Low A, Bentin S, Rockstroh B, Silberman Y, Gomolla A, Cohen R, Elbert T (2003) Semantic categorization in the human brain: spatiotemporal dynamics revealed by magneto encephalography. Psychol Sci 14(4):367–372

    Article  Google Scholar 

  • Moutarde F, Ultsch A (2005) U*F clustering: a new performant cluster mining method based on segmentation of self-organizing maps. Proceedings of WSOM ‘05. 5–8 September, Paris, France, pp 25–32

  • National Research Council (1996) Barriers to science. Technical management of the Department of Energy Environmental Remediation Program, Commission on Geosciences, Environment and Resources, National Research Council, Washington, DC

  • Pasion LR, Oldenburg DW (2001) Locating and characterizing unexploded ordnance using time domain electromagnetic induction, U.S. Army Corps of Engineers, ERDC/GSL TR-01-10

  • Polzlbauer G, Dittenbach M, Rauber A (2005) A visualization technique for self-organizing maps with vector fields to obtain the cluster structure at desired levels of detail. Proceedings of the IJCNN 2005, Montreal, Canada, p 7

  • Poulton MM, Sternberg BK, Glass CE (1992a) Location of subsurface targets in geophysical data using neural networks. Geophysics 57(12):1534–1544

    Article  Google Scholar 

  • Poulton MM, Sternberg BK, Glass CE (1992b) Neural network pattern recognition of subsurface EM images. J Appl Geophys 29(1):21–36

    Article  Google Scholar 

  • Scott DW (1992) Multivariate density estimation. Wiley, New York

    Google Scholar 

  • Smith R, Paine J (1999) Three-dimensional transient electromagnetic modeling— a user’s view, In: Oristaglio M, Spies B (eds) Three-dimensional electromagnetics, geophysical developments No. 5. SEG, Tulsa

    Google Scholar 

  • Stalnaker JL, Everett ME, Benavides A, Pierce Jr. CJ (2006) Mutual induction and the effect of host conductivity on the EM induction response of buried plate targets using 3-D finite-element analysis. IEEE Trans Geosci Remote Sens 44(2):251–259

    Article  Google Scholar 

  • Strecker U, Uden R (2002) Data mining of 3D post stack seismic attribute volumes using Kohonen self-organizing maps. Lead Edge 21:1032–1037

    Article  Google Scholar 

  • Ultsch A (2003a) Maps for the visualization of high-dimensional data spaces. Proceedings of WSOM ‘03, Fukuoka, Japan, pp 225–236

  • Ultsch A (2003b) U*-matrix: a tool to visualize clusters in high dimensional data Department of Computer Science, University of Marburg, Technical Report 36

Download references

Acknowledgments

The authors thank George Robitaille (Aberdeen Proving Ground) for providing us with an inert UXO kit, and two anonymous reviewers for the comments and suggestions that helped us to improve the paper. This work has been conducted under SERDP contract UX-1312.

Author information

Authors and Affiliations

  1. Department of Geology and Geophysics, Texas A&M University, College Station, TX, USA

    Alfonso Benavides I & Mark E. Everett

  2. Department of Geology, Saint Lawrence University, Canton, NY, USA

    Carl Pierce Jr.

Authors
  1. Alfonso Benavides I
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mark E. Everett
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Carl Pierce Jr.
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alfonso Benavides I.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Benavides I, A., Everett, M.E. & Pierce, C. Unexploded ordnance discrimination using time-domain electromagnetic induction and self-organizing maps. Stoch Environ Res Risk Assess 23, 169–179 (2009). https://doi.org/10.1007/s00477-007-0211-5

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00477-007-0211-5

Keywords

Search

Navigation